【摘要】：隨著互聯(lián)網(wǎng)中用戶、商品、交易記錄、社交信息等一系列數(shù)據(jù)的爆炸式增長,海量規(guī)模的信息資源充斥在網(wǎng)絡(luò)中,容易產(chǎn)生"信息過載"現(xiàn)象。為解決這一問題,個性化推薦技術(shù)應(yīng)運而生,它能夠為用戶提供符合其自身特性的信息服務(wù)和決策支持。協(xié)同過濾算法是個性化推薦技術(shù)中的熱門研究課題,其通過分析用戶行為,在用戶群體中挖掘其他與指定用戶興趣相仿的用戶,綜合這些相似用戶特征對目標(biāo)物品進行評分,形成推薦模塊對目標(biāo)物品的評分預(yù)測。然而,隨著數(shù)據(jù)規(guī)模的不斷增長,協(xié)同過濾推薦算法也面臨一系列挑戰(zhàn),諸如數(shù)據(jù)稀疏性問題、擴展性問題、推薦準(zhǔn)確性問題等。本文深入研究基于模型的協(xié)同過濾推薦算法中的數(shù)據(jù)稀疏性、可擴展性問題,并對基于受限玻爾茲曼機和基于矩陣奇異值分解的評分預(yù)測推薦算法進行改進。主要工作包括:第一,對傳統(tǒng)協(xié)同過濾推薦算法的體系結(jié)構(gòu)、發(fā)展現(xiàn)狀展開研究,對基于鄰居相似度和基于模型的協(xié)同過濾推薦算法分別作詳細介紹。深入研究RBM模型的網(wǎng)絡(luò)結(jié)構(gòu)、對比散度訓(xùn)練方法,詳細分析了奇異值分解(Singular Value Decomposition,簡記為SVD)模型的理論方法,對隱語義模型及正則化方法進行了詳細說明。第二,對基于RBM的協(xié)同過濾推薦算法進行改進,加入訓(xùn)練數(shù)據(jù)中用戶瀏覽過但未評分的行為信息,形成基于條件受限玻爾茲曼機(Conditional RBM,簡記為CRBM)的協(xié)同過濾預(yù)測算法,并對現(xiàn)有的針對用戶的CRBM進行改進,提出針對項目的CRBM模型。實驗結(jié)果表明,改進后針對項目的CRBM算法預(yù)測精度優(yōu)于目前針對用戶的CRBM協(xié)同過濾算法。第三,對基于用戶行為屬性的SVD++預(yù)測模型進行分析與改進,加入用戶歷史行為記錄的潛在信息,用包含用戶喜好的隱性特征向量矩陣替換原SVD模型中的用戶特征向量矩陣,提出非對稱奇異值分解算法(Asymmetric SVD,簡記為ASVD)及其對偶模型,并對提出的預(yù)測模型進行擴展,加入k近鄰關(guān)系形成融合推薦模型進行評分預(yù)測。實驗結(jié)果表明,所提出的融合模型能有效提高推薦系統(tǒng)的預(yù)測精度。
[Abstract]:With the explosive growth of a series of data such as users, commodities, transaction records, social information and so on in the Internet, massive information resources are flooded in the network, which is easy to produce the phenomenon of "information overload". In order to solve this problem, personalized recommendation technology emerged as the times require, which can provide users with information services and decision support according to their own characteristics. Collaborative filtering algorithm is a hot research topic in personalized recommendation technology. By analyzing user behavior, the collaborative filtering algorithm can mine other users with similar interests to specific users and score the target items by synthesizing these similar user characteristics. Form recommendation module to predict target item score. However, with the increasing of data scale, collaborative filtering recommendation algorithms face a series of challenges, such as data sparsity problem, scalability problem, recommendation accuracy problem and so on. In this paper, the data sparsity and extensibility of model-based collaborative filtering recommendation algorithm are studied in depth, and the evaluation prediction recommendation algorithm based on constrained Boltzmann machine and matrix singular value decomposition is improved. The main works are as follows: first, the architecture and development status of traditional collaborative filtering recommendation algorithms are studied, and the neighbor similarity and model-based collaborative filtering recommendation algorithms are introduced in detail. This paper deeply studies the network structure of RBM model, compares the divergence training method, analyzes in detail the theoretical method of singular value decomposition (Singular Value Decomposition,) model as SVD), and explains the implicit semantic model and regularization method in detail. Secondly, the collaborative filtering recommendation algorithm based on RBM is improved, and the behavior information that the user browses but does not score in the training data is added to form a collaborative filtering prediction algorithm based on conditional constrained Boltzmann machine (Conditional RBM, abbreviated as CRBM). The existing CRBM for users is improved, and the CRBM model for the project is proposed. The experimental results show that the prediction accuracy of the improved CRBM algorithm is better than that of the current CRBM collaborative filtering algorithm for users. Thirdly, the SVD prediction model based on user behavior attributes is analyzed and improved, and the latent information of user history behavior record is added to replace the user eigenvector matrix in the original SVD model with a recessive eigenvector matrix containing user preferences. An asymmetric singular value decomposition (Asymmetric SVD,) algorithm called ASVD) and its dual model are proposed. The proposed prediction model is extended and the k-nearest neighbor relationship is added to form the fusion recommendation model. Experimental results show that the proposed fusion model can effectively improve the prediction accuracy of the recommendation system.
【學(xué)位授予單位】：中國科學(xué)技術(shù)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.3

【參考文獻】

相關(guān)期刊論文 前9條

1 陳平華;陳傳瑜;洪英漢;;一種結(jié)合關(guān)聯(lián)規(guī)則的協(xié)同過濾推薦算法[J];小型微型計算機系統(tǒng);2016年02期

2 苗放;;面向數(shù)據(jù)的軟件體系結(jié)構(gòu)初步探討[J];計算機科學(xué)與探索;2016年10期

3 鄧青;馬曄風(fēng);劉藝;張輝;;基于BP神經(jīng)網(wǎng)絡(luò)的微博轉(zhuǎn)發(fā)量的預(yù)測[J];清華大學(xué)學(xué)報(自然科學(xué)版);2015年12期

4 何潔月;馬貝;;利用社交關(guān)系的實值條件受限玻爾茲曼機協(xié)同過濾推薦算法[J];計算機學(xué)報;2016年01期

5 孟祥武;劉樹棟;張玉潔;胡勛;;社會化推薦系統(tǒng)研究[J];軟件學(xué)報;2015年06期

6 張春霞;姬楠楠;王冠偉;;受限波爾茲曼機[J];工程數(shù)學(xué)學(xué)報;2015年02期

7 孫天凱;邵曉根;鞠訓(xùn)光;;基于對稱受限玻爾茲曼機的協(xié)同過濾算法[J];江蘇科技大學(xué)學(xué)報(自然科學(xué)版);2014年04期

8 潘金貴,胡學(xué)聯(lián),李俊,張靈玲;一個個性化的信息搜集Agent的設(shè)計與實現(xiàn)[J];軟件學(xué)報;2001年07期

9 馮翱,劉斌,盧增祥,路海明,王普,李衍達;Open Bookmark——基于Agent的信息過濾系統(tǒng)[J];清華大學(xué)學(xué)報(自然科學(xué)版);2001年03期

相關(guān)碩士學(xué)位論文 前1條

1 胡洋;基于馬爾可夫鏈蒙特卡羅方法的RBM學(xué)習(xí)算法改進[D];上海交通大學(xué);2012年

，

本文編號：2399195